Serper MCP Server
@garymengcom
About Serper MCP Server
A Serper MCP Server
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"serper": {
"command": "uvx",
"args": [
"serper-mcp-server"
],
"env": {
"SERPER_API_KEY": "<Your Serper API key>"
}
}
}
}Tools
13Search Google for results
Search Google for results
Search Google for results
Search Google for results
Search Google for results
Search Google for results
Search Google for results
Search Google for results
Search Google for results
Search Google for results
Search Google for results
Search Google for results
Scrape webpage by url
Overview
What is Serper MCP Server?
A Model Context Protocol server that provides Google Search via Serper, enabling LLMs to get search result information from Google. It requires Python 3.11+ and a Serper API key.
How to use Serper MCP Server?
Install via Smithery (npx -y @smithery/cli install @garylab/serper-mcp-server --client claude), uvx (recommended), or pip. Configure the SERPER_API_KEY environment variable in your MCP client (e.g., claude_desktop_config.json). The server exposes multiple search tools (e.g., google_search, google_search_images) that can be called by the LLM.
Key features of Serper MCP Server
- Provides 13 different Google search tool types (web, images, videos, places, maps, reviews, news, shopping, lens, scholar, patents, autocomplete).
- Includes a
webpage_scrapetool for scraping web page content. - Installable via Smithery,
uvx, orpip. - Requires only a Serper API key for authentication.
- Released under the MIT License.
Use cases of Serper MCP Server
- Enable an LLM to fetch up-to-date Google search results for user queries.
- Retrieve images, news, or shopping results programmatically through a chat interface.
- Scrape web page content to augment LLM responses with live data.
- Integrate Google search capabilities into AI assistants or automation tools.
FAQ from Serper MCP Server
What runtime does Serper MCP Server require?
Python 3.11 or higher. It can be run via uvx (using uv) or directly with python3 after pip install.
Where does the API key come from?
You must obtain a Serper API key from Serper (serper.dev) and set it as the SERPER_API_KEY environment variable.
What transports or authentication does it support?
It uses standard MCP transport (stdio) and authenticates via an environment variable (SERPER_API_KEY).
How can I debug the server?
Use the MCP Inspector: npx @modelcontextprotocol/inspector uvx serper-mcp-server or run from source with npx @modelcontextprotocol/inspector uv run serper-mcp-server -e SERPER_API_KEY=<key>.
Does the server have any known limitations?
The README does not mention any specific limitations beyond requiring Python 3.11+ and a valid Serper API key.
More Search MCP servers
Tavily Mcp
tavily-aiProduction ready MCP server with real-time search, extract, map & crawl.
Perplexity MCP Zerver
wysh3MCP web search using perplexity without any API KEYS
MCP SearXNG Enhanced Server
OvertliDSEnhanced MCP server for SearXNG: category-aware web-search, web-scraping, and date/time retrieval.
小红书自动搜索评论工具（MCP Server 2.0）
chenningling这是一款基于 Playwright 开发的小红书自动搜索和评论工具，作为 MCP Server，可通过特定配置接入 MCP Client（如Claude for Desktop），帮助用户自动完成登录小红书、搜索关键词、获取笔记内容及发布AI生成评论等操作。
mcp-omnisearch
spences10🔍 A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi, Exa), AI tools (Kagi FastGPT, Exa, Linkup), and content extraction services (Firecrawl, Tavily, Kagi). Includes GitHub search. All through a single interface.
Comments